Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging

Block layer patches

- virtio-scsi: add iothread-vq-mapping parameter
- Improve writethrough performance
- Fix missing zero init in bdrv_snapshot_goto()
- Added scripts/qcow2-to-stdout.py
- Code cleanup and iotests fixes

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmfTDysRHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9Yz6A//asOl37zjbtf9pYjY/gliH859TQOppPGD
# LB9IIr+nTDME0wfUkCOlag+CeEYZwkeo2PF+XeopsyzlJeBOk4tL7AkY57XYe3lZ
# M5hlnNrn6l3gb6iioMg60pEKSMrpKprB16vT3nAtyN6aEXsm9TvtPkWPFTCFGVeK
# W74VCr7wuXbfdEJcOGd8WhB9ZHIgwoWYnoL41tvCoefW2yNaMA6X0TLn98toXzOi
# il50ZnnchTQngns5R+n+1R1Ma995t393D+CArQcYVRzxKGOs5p0y4otz4gCkMhdp
# GVL09R7Ge4TteSJ2myxlN/EjYOxmdoMrVDajr4xPdHBw12MKzgk8i82h4/Es/Q5o
# 3Npgx74+jDyqlICb/czTVM5KJINpyO80vO3N3WpYUOQGyTCcYgv7pIpy8pB2o6Te
# RPlv0W9bHVSSgThFFLQ0Ud8WRGJe1K/ar8bdmiWN08Wez1avENWaYmsv5zGnFL24
# vD6cNXMR4mF7mzyeWda/5hGKv75djVgX+ZfzvWNT3qgizD56JBOA3RdCRwBZJOJb
# TvJkfi5RGyaji9BfKVCYBL3/iDELJEVDW8jxvIIUrS0aPcTHpAQ5gTO7VAokreqZ
# 5Smll11eeoEgPPvNLw8ikmOGTWOMkJGrmExP2K1ApANq3kSbBSU4jroEr0BG9PZT
# 6Y0hUdtFSdU=
# =w2Ri
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 14 Mar 2025 01:00:27 HKT
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "[email protected]"
# gpg: Good signature from "Kevin Wolf <[email protected]>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* tag 'for-upstream' of https://repo.or.cz/qemu/kevin: (23 commits)
  scripts/qcow2-to-stdout.py: Add script to write qcow2 images to stdout
  virtio-scsi: only expose cmd vqs via iothread-vq-mapping
  virtio-scsi: handle ctrl virtqueue in main loop
  virtio-scsi: add iothread-vq-mapping parameter
  virtio: extract iothread-vq-mapping.h API
  virtio-blk: tidy up iothread_vq_mapping functions
  virtio-blk: extract cleanup_iothread_vq_mapping() function
  virtio-scsi: perform TMFs in appropriate AioContexts
  virtio-scsi: protect events_dropped field
  virtio-scsi: introduce event and ctrl virtqueue locks
  scsi: introduce requests_lock
  scsi: track per-SCSIRequest AioContext
  dma: use current AioContext for dma_blk_io()
  scsi-disk: drop unused SCSIDiskState->bh field
  iotests: Limit qsd-migrate to working formats
  aio-posix: Adjust polling time also for new handlers
  aio-posix: Separate AioPolledEvent per AioHandler
  aio-posix: Factor out adjust_polling_time()
  aio: Create AioPolledEvent
  block/io: Ignore FUA with cache.no-flush=on
  ...

Signed-off-by: Stefan Hajnoczi <[email protected]>

Author: stefanhaRH

block/block-backend.c

@@ -2357,18 +2357,6 @@ void *blk_blockalign(BlockBackend *blk, size_t size)
     return qemu_blockalign(blk ? blk_bs(blk) : NULL, size);
 }
 
-bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
-{
-    BlockDriverState *bs = blk_bs(blk);
-    GLOBAL_STATE_CODE();
-    GRAPH_RDLOCK_GUARD_MAINLOOP();
-
-    if (!bs) {
-        return false;
-    }
-
-    return bdrv_op_is_blocked(bs, op, errp);
-}
 
 /**
  * Return BB's current AioContext.  Note that this context may change

block/file-posix.c

@@ -194,6 +194,7 @@ static int fd_open(BlockDriverState *bs)
 }
 
 static int64_t raw_getlength(BlockDriverState *bs);
+static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs);
 
 typedef struct RawPosixAIOData {
     BlockDriverState *bs;
@@ -804,6 +805,13 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
 #endif
     s->needs_alignment = raw_needs_alignment(bs);
 
+    bs->supported_write_flags = BDRV_REQ_FUA;
+    if (s->use_linux_aio && !laio_has_fua()) {
+        bs->supported_write_flags &= ~BDRV_REQ_FUA;
+    } else if (s->use_linux_io_uring && !luring_has_fua()) {
+        bs->supported_write_flags &= ~BDRV_REQ_FUA;
+    }
+
     bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK;
     if (S_ISREG(st.st_mode)) {
         /* When extending regular files, we get zeros from the OS */
@@ -2477,7 +2485,8 @@ static inline bool raw_check_linux_aio(BDRVRawState *s)
 #endif
 
 static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
-                                   uint64_t bytes, QEMUIOVector *qiov, int type)
+                                   uint64_t bytes, QEMUIOVector *qiov, int type,
+                                   int flags)
 {
     BDRVRawState *s = bs->opaque;
     RawPosixAIOData acb;
@@ -2508,13 +2517,13 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
 #ifdef CONFIG_LINUX_IO_URING
     } else if (raw_check_linux_io_uring(s)) {
         assert(qiov->size == bytes);
-        ret = luring_co_submit(bs, s->fd, offset, qiov, type);
+        ret = luring_co_submit(bs, s->fd, offset, qiov, type, flags);
         goto out;
 #endif
 #ifdef CONFIG_LINUX_AIO
     } else if (raw_check_linux_aio(s)) {
         assert(qiov->size == bytes);
-        ret = laio_co_submit(s->fd, offset, qiov, type,
+        ret = laio_co_submit(s->fd, offset, qiov, type, flags,
                               s->aio_max_batch);
         goto out;
 #endif
@@ -2534,6 +2543,10 @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, int64_t *offset_ptr,
 
     assert(qiov->size == bytes);
     ret = raw_thread_pool_submit(handle_aiocb_rw, &acb);
+    if (ret == 0 && (flags & BDRV_REQ_FUA)) {
+        /* TODO Use pwritev2() instead if it's available */
+        ret = raw_co_flush_to_disk(bs);
+    }
     goto out; /* Avoid the compiler err of unused label */
 
 out:
@@ -2571,14 +2584,14 @@ static int coroutine_fn raw_co_preadv(BlockDriverState *bs, int64_t offset,
                                       int64_t bytes, QEMUIOVector *qiov,
                                       BdrvRequestFlags flags)
 {
-    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_READ);
+    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_READ, flags);
 }
 
 static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, int64_t offset,
                                        int64_t bytes, QEMUIOVector *qiov,
                                        BdrvRequestFlags flags)
 {
-    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_WRITE);
+    return raw_co_prw(bs, &offset, bytes, qiov, QEMU_AIO_WRITE, flags);
 }
 
 static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
@@ -2600,12 +2613,12 @@ static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs)
 
 #ifdef CONFIG_LINUX_IO_URING
     if (raw_check_linux_io_uring(s)) {
-        return luring_co_submit(bs, s->fd, 0, NULL, QEMU_AIO_FLUSH);
+        return luring_co_submit(bs, s->fd, 0, NULL, QEMU_AIO_FLUSH, 0);
     }
 #endif
 #ifdef CONFIG_LINUX_AIO
     if (s->has_laio_fdsync && raw_check_linux_aio(s)) {
-        return laio_co_submit(s->fd, 0, NULL, QEMU_AIO_FLUSH, 0);
+        return laio_co_submit(s->fd, 0, NULL, QEMU_AIO_FLUSH, 0, 0);
     }
 #endif
     return raw_thread_pool_submit(handle_aiocb_flush, &acb);
@@ -3540,7 +3553,7 @@ static int coroutine_fn raw_co_zone_append(BlockDriverState *bs,
     }
 
     trace_zbd_zone_append(bs, *offset >> BDRV_SECTOR_BITS);
-    return raw_co_prw(bs, offset, len, qiov, QEMU_AIO_ZONE_APPEND);
+    return raw_co_prw(bs, offset, len, qiov, QEMU_AIO_ZONE_APPEND, 0);
 }
 #endif
 

block/io.c

@@ -1058,6 +1058,10 @@ bdrv_driver_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
         return -ENOMEDIUM;
     }
 
+    if (bs->open_flags & BDRV_O_NO_FLUSH) {
+        flags &= ~BDRV_REQ_FUA;
+    }
+
     if ((flags & BDRV_REQ_FUA) &&
         (~bs->supported_write_flags & BDRV_REQ_FUA)) {
         flags &= ~BDRV_REQ_FUA;

block/io_uring.c

@@ -335,15 +335,24 @@ static void luring_deferred_fn(void *opaque)
  *
  */
 static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
-                            uint64_t offset, int type)
+                            uint64_t offset, int type, BdrvRequestFlags flags)
 {
     int ret;
     struct io_uring_sqe *sqes = &luringcb->sqeq;
 
     switch (type) {
     case QEMU_AIO_WRITE:
+#ifdef HAVE_IO_URING_PREP_WRITEV2
+    {
+        int luring_flags = (flags & BDRV_REQ_FUA) ? RWF_DSYNC : 0;
+        io_uring_prep_writev2(sqes, fd, luringcb->qiov->iov,
+                              luringcb->qiov->niov, offset, luring_flags);
+    }
+#else
+        assert(flags == 0);
         io_uring_prep_writev(sqes, fd, luringcb->qiov->iov,
                              luringcb->qiov->niov, offset);
+#endif
         break;
     case QEMU_AIO_ZONE_APPEND:
         io_uring_prep_writev(sqes, fd, luringcb->qiov->iov,
@@ -380,7 +389,8 @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
 }
 
 int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset,
-                                  QEMUIOVector *qiov, int type)
+                                  QEMUIOVector *qiov, int type,
+                                  BdrvRequestFlags flags)
 {
     int ret;
     AioContext *ctx = qemu_get_current_aio_context();
@@ -393,7 +403,7 @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset,
     };
     trace_luring_co_submit(bs, s, &luringcb, fd, offset, qiov ? qiov->size : 0,
                            type);
-    ret = luring_do_submit(fd, &luringcb, s, offset, type);
+    ret = luring_do_submit(fd, &luringcb, s, offset, type, flags);
 
     if (ret < 0) {
         return ret;
@@ -448,3 +458,12 @@ void luring_cleanup(LuringState *s)
     trace_luring_cleanup_state(s);
     g_free(s);
 }
+
+bool luring_has_fua(void)
+{
+#ifdef HAVE_IO_URING_PREP_WRITEV2
+    return true;
+#else
+    return false;
+#endif
+}

block/linux-aio.c

@@ -368,15 +368,24 @@ static void laio_deferred_fn(void *opaque)
 }
 
 static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
-                          int type, uint64_t dev_max_batch)
+                          int type, BdrvRequestFlags flags,
+                          uint64_t dev_max_batch)
 {
     LinuxAioState *s = laiocb->ctx;
     struct iocb *iocbs = &laiocb->iocb;
     QEMUIOVector *qiov = laiocb->qiov;
 
     switch (type) {
     case QEMU_AIO_WRITE:
+#ifdef HAVE_IO_PREP_PWRITEV2
+    {
+        int laio_flags = (flags & BDRV_REQ_FUA) ? RWF_DSYNC : 0;
+        io_prep_pwritev2(iocbs, fd, qiov->iov, qiov->niov, offset, laio_flags);
+    }
+#else
+        assert(flags == 0);
         io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
+#endif
         break;
     case QEMU_AIO_ZONE_APPEND:
         io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
@@ -409,7 +418,8 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
 }
 
 int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
-                                int type, uint64_t dev_max_batch)
+                                int type, BdrvRequestFlags flags,
+                                uint64_t dev_max_batch)
 {
     int ret;
     AioContext *ctx = qemu_get_current_aio_context();
@@ -422,7 +432,7 @@ int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
         .qiov       = qiov,
     };
 
-    ret = laio_do_submit(fd, &laiocb, offset, type, dev_max_batch);
+    ret = laio_do_submit(fd, &laiocb, offset, type, flags, dev_max_batch);
     if (ret < 0) {
         return ret;
     }
@@ -505,3 +515,12 @@ bool laio_has_fdsync(int fd)
     io_destroy(ctx);
     return (ret == -EINVAL) ? false : true;
 }
+
+bool laio_has_fua(void)
+{
+#ifdef HAVE_IO_PREP_PWRITEV2
+    return true;
+#else
+    return false;
+#endif
+}

block/snapshot.c

@@ -296,6 +296,7 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
         bdrv_graph_wrunlock();
 
         ret = bdrv_snapshot_goto(fallback_bs, snapshot_id, errp);
+        memset(bs->opaque, 0, drv->instance_size);
         open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err);
         qobject_unref(options);
         if (open_ret < 0) {